1
|
Şahin D, Kambeitz-Ilankovic L, Wood S, Dwyer D, Upthegrove R, Salokangas R, Borgwardt S, Brambilla P, Meisenzahl E, Ruhrmann S, Schultze-Lutter F, Lencer R, Bertolino A, Pantelis C, Koutsouleris N, Kambeitz J. Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis. Br J Psychiatry 2024; 224:55-65. [PMID: 37936347 DOI: 10.1192/bjp.2023.141] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/09/2023]
Abstract
BACKGROUND Computational models offer promising potential for personalised treatment of psychiatric diseases. For their clinical deployment, fairness must be evaluated alongside accuracy. Fairness requires predictive models to not unfairly disadvantage specific demographic groups. Failure to assess model fairness prior to use risks perpetuating healthcare inequalities. Despite its importance, empirical investigation of fairness in predictive models for psychiatry remains scarce. AIMS To evaluate fairness in prediction models for development of psychosis and functional outcome. METHOD Using data from the PRONIA study, we examined fairness in 13 published models for prediction of transition to psychosis (n = 11) and functional outcome (n = 2) in people at clinical high risk for psychosis or with recent-onset depression. Using accuracy equality, predictive parity, false-positive error rate balance and false-negative error rate balance, we evaluated relevant fairness aspects for the demographic attributes 'gender' and 'educational attainment' and compared them with the fairness of clinicians' judgements. RESULTS Our findings indicate systematic bias towards assigning less favourable outcomes to individuals with lower educational attainment in both prediction models and clinicians' judgements, resulting in higher false-positive rates in 7 of 11 models for transition to psychosis. Interestingly, the bias patterns observed in algorithmic predictions were not significantly more pronounced than those in clinicians' predictions. CONCLUSIONS Educational bias was present in algorithmic and clinicians' predictions, assuming more favourable outcomes for individuals with higher educational level (years of education). This bias might lead to increased stigma and psychosocial burden in patients with lower educational attainment and suboptimal psychosis prevention in those with higher educational attainment.
Collapse
Affiliation(s)
- Derya Şahin
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany
| | - Lana Kambeitz-Ilankovic
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany; and Department of Psychology, Faculty of Psychology and Educational Sciences, Ludwig-Maximilian University, Munich, Germany
| | - Stephen Wood
- Centre for Youth Mental Health, University of Melbourne, Melbourne, Victoria, Australia; and Orygen, the National Centre of Excellence for Youth Mental Health, Melbourne, Victoria, Australia
| | - Dominic Dwyer
- Department of Psychology, Faculty of Psychology and Educational Sciences, Ludwig-Maximilian University, Munich, Germany; and Orygen, the National Centre of Excellence for Youth Mental Health, Melbourne, Victoria, Australia
| | - Rachel Upthegrove
- Institute for Mental Health and Centre for Brain Health, University of Birmingham, Birmingham, UK; and Early Intervention Service, Birmingham Women's and Children's NHS Foundation Trust, Birmingham, UK
| | | | - Stefan Borgwardt
- Department of Psychiatry (University Psychiatric Clinics, UPK), University of Basel, Basel, Switzerland; and Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany
| | - Paolo Brambilla
- Department of Neurosciences and Mental Health, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy; and Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy
| | - Eva Meisenzahl
- Department of Psychiatry and Psychotherapy, Medical Faculty, Heinrich Heine University, Düsseldorf, Germany
| | - Stephan Ruhrmann
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany
| | - Frauke Schultze-Lutter
- Department of Psychiatry and Psychotherapy, Medical Faculty, Heinrich Heine University, Düsseldorf, Germany; Department of Psychology, Faculty of Psychology, Airlangga University, Surabaya, Indonesia; and University Hospital of Child and Adolescent Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland
| | - Rebekka Lencer
- Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany; and Institute for Translational Psychiatry, University of Münster, Münster, Germany
| | - Alessandro Bertolino
- Department of Basic Medical Science, Neuroscience and Sense Organs, University of Bari Aldo Moro, Bari, Italy
| | - Christos Pantelis
- Melbourne Neuropsychiatry Centre, University of Melbourne & Melbourne Health, Melbourne, Victoria, Australia
| | - Nikolaos Koutsouleris
- Department of Psychology, Faculty of Psychology and Educational Sciences, Ludwig-Maximilian University, Munich, Germany; Max-Planck Institute of Psychiatry, Munich, Germany; and Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - Joseph Kambeitz
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany
| |
Collapse
|
2
|
Walter N, Wenzel J, Haas SS, Squarcina L, Bonivento C, Ruef A, Dwyer D, Lichtenstein T, Bastrük Ö, Stainton A, Antonucci LA, Brambilla P, Wood SJ, Upthegrove R, Borgwardt S, Lencer R, Meisenzahl E, Salokangas RKR, Pantelis C, Bertolino A, Koutsouleris N, Kambeitz J, Kambeitz-Ilankovic L. A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training. Prog Neuropsychopharmacol Biol Psychiatry 2024; 128:110864. [PMID: 37717645 DOI: 10.1016/j.pnpbp.2023.110864] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Revised: 08/01/2023] [Accepted: 09/13/2023] [Indexed: 09/19/2023]
Abstract
Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S < 7) functioning patients based on their level of Global Functioning-Social (GF-S) score at follow-up (FU). By applying the initial PRONIA classifier, using out-of-sample cross-validation (OOCV) to the sample of ROP patients who have undergone the CT intervention, a BAC of 59.3% (Sensitivity 70.4%; Specificity 48.1%; PPV 57.6%; NPV 61.9%; AUC 0.63) was achieved at T0 and a BAC of 64.8% (Sensitivity 66.7%; Specificity 63.0%; PPV 64.3%; NPV 65.4%; AUC 0.66) at FU. After SCT intervention, a significant improvement in predicted social functioning values was observed in the SCT compared to TAU group (P ≤0.05; ES[Cohens' d] = 0.18). Due to a small sample size and modest variance of social functioning of the intervention sample it was not feasible to predict individual response to SCT in the current study. Our findings suggest that the use of baseline cognitive data could provide a robust individual estimate of future social functioning, while prediction of individual response to SCT using cognitive data that can be generated in the routine patient care remains to be addressed in large-scale cognitive training trials.
Collapse
Affiliation(s)
- Nina Walter
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany
| | - Julian Wenzel
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany
| | - Shalaila S Haas
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, NY, New York, United States of America
| | | | | | - Anne Ruef
- Department of Psychiatry and Psychotherapy, Ludwig-Maximilian University, Munich, Germany
| | - Dominic Dwyer
- Department of Psychiatry and Psychotherapy, Ludwig-Maximilian University, Munich, Germany; Orygen Youth Health, Melbourne, Australia; Centre for Youth Mental Health, University of Melbourne, Melbourne, Australia
| | - Theresa Lichtenstein
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany
| | - Öznur Bastrük
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany
| | - Alexandra Stainton
- Orygen Youth Health, Melbourne, Australia; Centre for Youth Mental Health, University of Melbourne, Melbourne, Australia
| | - Linda A Antonucci
- Department of Translational Biomedicine and Neuroscience, University of Bari Aldo Moro, Bari, Italy
| | - Paolo Brambilla
- Department of Neuosciences and Mental Health, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy; Department of Pathophysiology and Mental Health, University of Milan, Milan, Italy
| | - Stephen J Wood
- Orygen Youth Health, Melbourne, Australia; School of Psychology, University of Birmingham, United Kingdom; Centre for Youth Mental Health, University of Melbourne, Melbourne, Australia
| | - Rachel Upthegrove
- School of Psychology, University of Birmingham, United Kingdom; Institute of Mental Health, University of Birmingham, Birmingham, United Kingdom
| | - Stefan Borgwardt
- Translational Psychiatry Unit (TPU), Department of Psychiatry and Psychotherapy, University of Luebeck, Germany
| | - Rebekka Lencer
- Translational Psychiatry Unit (TPU), Department of Psychiatry and Psychotherapy, University of Luebeck, Germany
| | - Eva Meisenzahl
- Department of Psychiatry and Psychotherapy, Medical Faculty, Heinrich-Heine University, Düsseldorf, Germany
| | | | - Christos Pantelis
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, University of Melbourne & NorthWestern Mental Health, Melbourne, Australia
| | - Alessandro Bertolino
- Department of Translational Biomedicine and Neuroscience, University of Bari Aldo Moro, Bari, Italy
| | - Nikolaos Koutsouleris
- Department of Psychiatry and Psychotherapy, Ludwig-Maximilian University, Munich, Germany; Max Planck Institute for Psychiatry, Munich, Germany; Institute of Psychiatry, Psychology & Neuroscience, Department of Psychosis Studies, King's College London, London, United Kingdom
| | - Joseph Kambeitz
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany
| | - Lana Kambeitz-Ilankovic
- Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Kerpenerstr.62, 50931, Cologne, Germany; Faculty of Psychology and Educational Sciences, Department of Psychology, Ludwig-Maximilian University, Munich, Germany.
| |
Collapse
|
3
|
Hinkley LBN, Haas SS, Cheung SW, Nagarajan SS, Subramaniam K. Reduced neural connectivity in the caudate anterior head predicts hallucination severity in schizophrenia. Schizophr Res 2023; 261:1-5. [PMID: 37678144 PMCID: PMC10878029 DOI: 10.1016/j.schres.2023.08.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/28/2023] [Revised: 06/13/2023] [Accepted: 08/31/2023] [Indexed: 09/09/2023]
Abstract
BACKGROUND Caudate functional abnormalities have been identified as one critical neural substrate underlying sensory gating impairments that lead to auditory phantom hallucinations in both patients with schizophrenia (SZ) and tinnitus, characterized by the perception of internally generated sounds in the absence of external environmental auditory stimuli. In this study, we tested the hypothesis as to whether functional connectivity abnormalities in distinct caudate subdivisions implicated in sensory gating and auditory phantom percepts in tinnitus, which are currently being localized for neuromodulation targeting using deep brain stimulation techniques, would be associated with auditory phantom hallucination severity in SZ. METHODS Twenty five SZ and twenty eight demographically-matched healthy control (HC) participants, completed this fMRI resting-state study and clinical assessments. RESULTS Between-group seed-to-voxel analyses revealed only one region, the caudate anterior head, which showed reduced functional connectivity with the thalamus that survived whole-brain multiple comparison corrections. Importantly, connectivity between the caudate anterior head with thalamus negatively correlated with hallucination severity. CONCLUSIONS In the present study, we deliver the first evidence of caudate subdivision specificity for the neural pathophysiology underlying hallucinations in schizophrenia within a sensory gating framework that has been developed for auditory phantoms in patients with tinnitus. Our findings provide transdiagnostic convergent evidence for the role of the caudate in the gating of auditory phantom hallucinations, observed across patients with SZ and tinnitus by specifying the anterior caudate division is key to mediation of hallucinations, and creating a path towards personalized treatment approaches to arrest auditory phantom hallucinations from reaching perceptual awareness.
Collapse
Affiliation(s)
- Leighton B N Hinkley
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA 94143, USA
| | - Shalaila S Haas
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, NY 10029, USA
| | - Steven W Cheung
- Department of Otolaryngology-Head and Neck Surgery, University of California, San Francisco, CA 94143, USA; Surgical Services, San Francisco Veterans Health Care System, San Francisco, CA 94121, USA
| | - Srikantan S Nagarajan
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA 94143, USA
| | - Karuna Subramaniam
- Department of Psychiatry and Behavioral Sciences, University of California, San Francisco, CA 94143, USA.
| |
Collapse
|
4
|
Ophey A, Wenzel J, Paul R, Giehl K, Rehberg S, Eggers C, Reker P, van Eimeren T, Kalbe E, Kambeitz-Ilankovic L. Cognitive Performance and Learning Parameters Predict Response to Working Memory Training in Parkinson's Disease. JOURNAL OF PARKINSON'S DISEASE 2022; 12:2235-2247. [PMID: 36120792 PMCID: PMC9661332 DOI: 10.3233/jpd-223448] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Accepted: 08/23/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND Working memory (WM) training (WMT) is a popular intervention approach against cognitive decline in patients with Parkinson's disease (PD). However, heterogeneity in WM responsiveness suggests that WMT may not be equally efficient for all patients. OBJECTIVE The present study aims to evaluate a multivariate model to predict post-intervention verbal WM in patients with PD using a supervised machine learning approach. We test the predictive potential of novel learning parameters derived from the WMT and compare their predictiveness to other more commonly used domains including demographic, clinical, and cognitive data. METHODS 37 patients with PD (age: 64.09±8.56, 48.6% female, 94.7% Hoehn & Yahr stage 2) participated in a 5-week WMT. Four random forest regression models including 1) cognitive variables only, 2) learning parameters only, 3) both cognitive and learning variables, and 4) the entire set of variables (with additional demographic and clinical data, 'all' model), were built to predict immediate and 3-month-follow-up WM. RESULT The 'all' model predicted verbal WM with the lowest root mean square error (RMSE) compared to the other models, at both immediate (RMSE = 0.184; 95% -CI=[0.184;0.185]) and 3-month follow-up (RMSE = 0.216; 95% -CI=[0.215;0.217]). Cognitive baseline parameters were among the most important predictors in the 'all' model. The model combining cognitive and learning parameters significantly outperformed the model solely based on cognitive variables. CONCLUSION Commonly assessed demographic, clinical, and cognitive variables provide robust prediction of response to WMT. Nonetheless, inclusion of training-inherent learning parameters further boosts precision of prediction models which in turn may augment training benefits following cognitive interventions in patients with PD.
Collapse
Affiliation(s)
- Anja Ophey
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Medical Psychology | Neuropsychology & Gender Studies, Center for Neuropsychological Diagnostic and Intervention (CeNDI), Cologne, Germany
| | - Julian Wenzel
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Psychiatry and Psychotherapy, Cologne, Germany
| | - Riya Paul
- Department of Psychiatry and Psychotherapy, Ludwig-Maximilians-University, Munich, Germany
| | - Kathrin Giehl
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Nuclear Medicine, Cologne, Germany
- Research Centre Jülich, Institute of Neuroscience and Medicine (INM-2), Jülich, Germany
| | - Sarah Rehberg
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Medical Psychology | Neuropsychology & Gender Studies, Center for Neuropsychological Diagnostic and Intervention (CeNDI), Cologne, Germany
| | - Carsten Eggers
- Department of Neurology, University Hospital of Marburg, Marburg, Germany
- Center for Mind, Brain and Behavior - CMBB, Universities of Marburg and Gießen, Marburg, Germany
- Department of Neurology, Knappschaftskrankenhaus Bottrop, Bottrop, Germany
| | - Paul Reker
- Department of Neurology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Thilo van Eimeren
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Nuclear Medicine, Cologne, Germany
- Department of Neurology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Elke Kalbe
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Medical Psychology | Neuropsychology & Gender Studies, Center for Neuropsychological Diagnostic and Intervention (CeNDI), Cologne, Germany
| | - Lana Kambeitz-Ilankovic
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Psychiatry and Psychotherapy, Cologne, Germany
- Faculty of Psychology and Educational Sciences, Department of Psychology, Ludwig-Maximilian University, Munich, Germany
| |
Collapse
|